INDEX

Explanations

-made

np_max-act · gemini-2.0-flash

New Auto-Interp

Configuration

mwhanna/qwen3-4b-transcoders/layer_11.safetensors

Prompts (Dashboard)

16,384 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

163,840

Data Type

float32

Hook Name

blocks.11.mlp.hook_in

Architecture

transcoder

Context Size

8,192

Dataset

monology/pile-uncopyrighted

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

IMATION

-0.30

éĤķ

-0.27

lette

-0.26

ä¿³

-0.26

manufact

-0.25

okit

-0.25

Ð¿Ð¸ÑģÑĮ

-0.24

!.↵↵

-0.24

wick

-0.24

yper

-0.24

POSITIVE LOGITS

kah

0.27

 worms

0.27

bers

0.26

ety

0.25

ask

0.25

illet

0.25

 flashed

0.25

[]

0.25

quired

0.25

=forms

0.25

Activations Density 0.002%

-made

No Comments

No Known Activations